Wei Cheng
Senior Researcher, StepFun
I am a Senior Researcher at StepFun, where I work with Dr. Gang Yu. My current research centers on edge-side multimodal foundation models — unifying conversational, multimodal-understanding, and agentic capabilities in a single model. I am also broadly interested in AIGC image foundation models, with a particular focus on image editing and controllable generation.
Earlier in my career, I spent several years on 3D vision and computer graphics. Before StepFun, I held research positions at Tencent and SenseTime Research. I graduated from the Hong Kong University of Science and Technology, where I was fortunate to be advised by Prof. Lu Fang and Prof. Yebin Liu.
News
- Jun 2026 We are recruiting research interns on edge-side foundation models — feel free to contact me if interested!
- Mar 2026 5 papers accepted to CVPR 2026
- Feb 2026 2 papers accepted to ICLR 2026
- Sep 2025 3 papers accepted to NeurIPS 2025
- Apr 2025 Released Step1X-Edit and Step1X-3D, our team's open-source projects
- Feb 2025 MVPaint accepted to CVPR 2025
Selected Publications
View all →MVPaint: Synchronized Multi-View Diffusion for Painting Anything 3D
Wei Cheng*†, Juncheng Mu*, Xianfang Zeng, Xin Chen, Anqi Pang, Chi Zhang, Zhibin Wang, Bin Fu, Gang Yu, Ziwei Liu, Liang Pan
OmniSVG: A Unified Scalable Vector Graphics Generation Model
Yiying Yang*, Wei Cheng*, Sijin Chen, Xianfang Zeng, Fukun Yin, Jiaxu Zhang, Liao Wang, Gang Yu, Xingjun Ma, Yu-Gang Jiang
Step1X-Edit: A Practical Framework for General Image Editing
Shiyu Liu, Yucheng Han, Peng Xing, Fukun Yin, Rui Wang, Wei Cheng, Jiaqi Liao, Yingming Wang, Honghao Fu, Chunrui Han, Guopeng Li, Yuang Peng, Quan Sun, Jingwei Wu, Yan Cai, Zheng Ge, Ranchen Ming, Lei Xia, Xianfang Zeng, Yibo Zhu, Binxing Jiao, Xiangyu Zhang, Gang Yu, Daxin Jiang